Development of real-time character recognition system for the steel-iron plant

This paper describes about the development of real-time recognition system for the characters, which was marked at the slab and billet material in the steel-iron plant. Normally, the billets or slabs are mixed at yard so that their identifications are hardly tractable. The characters of these material image can be marked by use three kinds of methods such as auto marking machine, template-marking plate and hand written method. For the recognition of each character, we use KLT, PSV, and CCD & PSVM algorithm for the printed font, template-marked font and hand written font respectively. The font style of slab materials is printer letter. The font style of bloom or billet materials is mixed type with printed font, template-marked font and hand written font. For the application of recognition algorithm, we have developed vision system and installed at the slab and billet processing line of the steel-iron plant. Through the test, we have confirmed that our system has good performance and high recognition rate, 97.6% for slab and 98.6% for billet.